In Python either using Kaggle or Jupyter.

1. Use "FIFA 22 complete player dataset from Kaggle, players_22.csv" from lab2 2. Use the same columns and the standardization method specified in lab2. 3. Apply hierarchical method using ward method in scipy package. 4. Use dendrogram to find the best value of the number of clusters that should be for this dataset (in your opinion where is the best cute in the dendrogram). 5. Compare the number of clusters you chose using dendrogram to elbow method you used in lab2, is there a difference? And which methods you would prefer to find the number of clusters and why? 6. Apply Agglomerative Clustering in sklearn with the best value of the number of clusters you found in step 4 7. Visualize the resulting cluster using 3D visualization (you can reuse the code in the notebook given in the lab), choose "potential", "wage_eur", "value_eur" as x,y,z axis. 8. Read about ward method and explain how this method calculate the distance between clusters